Sreenivas R. Sukumar

Shape analysis algorithm based on information theory

In this paper, we describe an algorithm to measure the shape complexity for discrete approximations of planar curves in 2D images and manifold surfaces for 3D triangle meshes. We base our algorithm on shape curvature, and thus we compute shape information as the entropy of curvature. We present definitions to estimate curvature for both discrete curves and surfaces and then formulate our theory of shape information from these definitions. We demonstrate our algorithm with experimental results.

Towards understanding what makes 3D objects appear simple or complex

Humans perceive some objects more complex than others and learning or describing a particular object is directly related to the judged complexity. Towards the goal of understanding why the geometry of some 3D objects appear more complex than others, we conducted a psychophysical study and identified contributing attributes. Our experiments conclude that surface variation, symmetry, part count, simpler part decomposability, intricate details and topology are six significant dimensions that influence 3D visual shape complexity. With that knowledge, we present a method of quantifying complexity and show that the informational aspect of Shannonpsilas theory agrees with the human notion of shape complexity.

Multi-sensor integration for unmanned terrain modeling

State-of-the-art unmanned ground vehicles are capable of understanding and adapting to arbitrary road terrain for navigation. The robotic mobility platforms mounted with sensors detect and report security concerns for subsequent action. Often, the information based on the localization of the unmanned vehicle is not sufficient for deploying army resources. In such a scenario, a three dimensional (3D) map of the area that the ground vehicle has surveyed in its trajectory would provide a priori spatial knowledge for directing resources in an efficient manner. To that end, we propose a mobile, modular imaging system that incorporates multi-modal sensors for mapping unstructured arbitrary terrain. Our proposed system leverages 3D laser-range sensors, video cameras, global positioning systems (GPS) and inertial measurement units (IMU) towards the generation of photo-realistic, geometrically accurate, geo-referenced 3D terrain models. Based on the summary of the state-of-the-art systems, we address the need and hence several challenges in the real-time deployment, integration and visualization of data from multiple sensors. We document design issues concerning each of these sensors and present a simple temporal alignment method to integrate multi-sensor data into textured 3D models. These 3D models, in addition to serving as a priori for path planning, can also be used in simulators that study vehicle-terrain interaction. Furthermore, we show our 3D models possessing the required accuracy even for crack detection towards road surface inspection in airfields and highways.

Shape Measure for Identifying Perceptually Informative Parts of 3D Objects

We propose a mathematical approach for quantifying shape complexity of 3D surfaces based on perceptual principles of visual saliency. Our curvature variation measure (CVM), as a 3D feature, combines surface curvature and information theory by leveraging bandwidth-optimized kernel density estimators. Using a part decomposition algorithm for digitized 3D objects, represented as triangle meshes, we apply our shape measure to transform the low level mesh representation into a perceptually informative form. Further, we analyze the effects of noise, sensitivity to digitization, occlusions, and descriptiveness to demonstrate our shape measure on laser-scanned real world 3D objects.

Robotic three-dimensional imaging system for under-vehicle inspection

We present our research efforts toward the deployment of 3-D sensing technology to an under-vehicle inspection robot. The 3-D sensing modality provides flexibility with ambient lighting and illumination in addition to the ease of visualization, mobility, and in- creased confidence toward inspection. We leverage laser-based range-imaging techniques to reconstruct the scene of interest and address various design challenges in the scene modeling pipeline. On these 3-D mesh models, we propose a curvature-based surface feature toward the interpretation of the reconstructed 3-D geometry. The curvature variation measure (CVM) that we define as the en- tropic measure of curvature quantifies surface complexity indicative of the information present in the surface. We are able to segment the digitized mesh models into smooth patches and represent the automotive scene as a graph network of patches. The CVM at the nodes of the graph describes the surface patch. We demonstrate the descriptiveness of the CVM on manufacturer CAD and laser-

Mobile scanning system for the fast digitization of existing roadways and structures

Purpose – To present a Mobile Scanning System for digitizing three‐dimensional (3D) models of real‐world terrain.Design/methodology/approach – A combination of sensors (video, laser range, positioning, orientation) is placed on a mobile platform, which moves past the scene to be digitized. Data fusion from the sensors is performed to construct an accurate 3D model of the target environment.Findings – The developed system can acquire accurate models of real‐world environments in real time, at resolutions suitable for a variety of tasks.Originality/value – Treating the individual subsystems of the mobile scanning system independently yields a robust system that can be easily reconfigured on the fly for a variety of scanning scenarios.

Surface shape description of 3D data from under vehicle inspection robot

Our research efforts focus on the deployment of 3D sensing capabilities to a multi-modal under vehicle inspection robot. In this paper, we outline the various design challenges towards the automation of the 3D scene modeling task. We employ laser-based range imaging techniques to extract the geometry of a vehicles undercarriage and present our results after range integration. We perform shape analysis on the digitized triangle mesh models by segmenting them into smooth surface patches based on the curvedness of the surface. Using a region-growing procedure, we then obtain the patch adjacency. On each of these patches, we apply our definition of the curvature variation measure (CVM) as a descriptor of surface shape complexity. We base the information-theoretic CVM on shape curvature, and extract shape information as the entropic measure of curvature to represent a component as a graph network of patches. The CVM at the nodes of the graph describe the surface patch. We then demonstrate our algorithm with results on automotive components. With apriori manufacturer information about the CAD models in the undercarriage we approach the technical challenge of threat detection with our surface shape description algorithm on the laser scanned geometry.

Uncertainty minimization in multi-sensor localization systems using model selection theory

Belief propagation methods are the state-of-the-art with multisensor state localization problems. However, when localization applications have to deal with multimodality sensors whose functionality depends on the environment of operation, we understand the need for an inference framework to identify confident and reliable sensors. Such a framework helps eliminate failed/non-functional sensors from the fusion process minimizing uncertainty while propagating belief. We derive a framework inspired from model selection theory and demonstrate results on real world multisensor robot state localization and multicamera target tracking applications.

On handling uncertainty in the fundamental matrix for scene and motion adaptive pose recovery

The estimation of the fundamental matrix is the key step in feature-based camera ego-motion estimation for applications in scene modeling and vehicle navigation. In this paper, we present a new method of analyzing and further reducing the risk in the fundamental matrix due to the choice of a particular feature detector, the choice of the matching algorithm, the motion model, iterative hypothesis generation and verification paradigms. Our scheme makes use of model-selection theory to guide the switch to optimal methods for fundamental matrix estimation within the hypothesis-and-test architecture. We demonstrate our proposed method for vision-based robot localization in large-scale environments where the environment is constantly changing and navigation within the environment is unpredictable.

Thermal Modeling and Imaging of As-built Vehicle Components

This paper addresses the issue of thermal modeling of vehicle components where the 3D models of the components are not traditional CAD models derived from engineering drawings but are models derived from 3Dimaging scans of existing real-world objects. A “reverse engineering” pipeline is presented that uses 3D scanners to capture the geometry of an existing object from different views and then integrates these multiple views into a single 3D surface mesh description of the object. This process requires no a priori CAD drawings of the object and thus enables modeling in situations where the original manufacturer no longer exists or soldiers have made undocumented field modifications. The paper further discusses the use of these generated 3D models to simulate thermal imaging properties of the object using the Multi Service Electro-Optic Signature (MuSES) software. Thus, given an object of interest, this paper explores, first generating a 3D model of the object and, second, analyzing the thermal signature through simulation. As a third step, this paper investigates the experimental achievability and limitations of thermal image simulation of vehicle components.